HCS: A New Local Search Strategy for Memetic Multiobjective Evolutionary Algorithms

Lara, Adriana; Sánchez, Gustavo; Coello, Carlos A. Coello; Schütze, Oliver

doi:10.1109/tevc.2009.2024143

Cited by 169 publications

(68 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As these search behaviors are based on gradients, these methods cannot be used if objectives are not differentiable. Lara et al [2] suggest a novel iterative search procedure, Hill Climber with Sidestep (HCS), in which it is capable of moving both toward and along the Pareto set depending on the distance of the current iterate toward this set. The search direction selection is on the basis of the dominance relation between several trial vectors and the old individual.…”

Section: Multiarmed Banditmentioning

confidence: 99%

“…The first generation of intelligence algorithms for MOPs represented by NSGA [4], NPGA [5], and MOGA [6] were presented in 1990s. In 2000s, the second generation appeared, and the renowned ones include NSGA-II [7], SPEA-II [8], MOEA/D [9], and some biology imitated algorithms, such as MOPSO [2], MOIA [10], MOACO [11]. These algorithms are usually classified into 3 categories: Pareto based methods [4][5][6][7][8], indicator-based methods [12], and decomposition-based methods [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Latest Stored Information Based Adaptive Selection Strategy for Multiobjective Evolutionary Algorithm

Gao

Qing-hua

Fan

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The adaptive operator selection (AOS) and the adaptive parameter control are widely used to enhance the search power in many multiobjective evolutionary algorithms. This paper proposes a novel adaptive selection strategy with bandits for the multiobjective evolutionary algorithm based on decomposition (MOEA/D), named latest stored information based adaptive selection (LSIAS). An improved upper confidence bound (UCB) method is adopted in the strategy, in which the operator usage rate and abandonment of extreme fitness improvement are introduced to improve the performance of UCB. The strategy uses a sliding window to store recent valuable information about operators, such as factors, probabilities, and efficiency. Four common used DE operators are chosen with the AOS, and two kinds of assist information on operator are selected to improve the operators search power. The operator information is updated with the help of LSIAS and the resulting algorithmic combination is called MOEA/D-LSIAS. Compared to some well-known MOEA/D variants, the LSIAS demonstrates the superior robustness and fast convergence for various multiobjective optimization problems. The comparative experiments also demonstrate improved search power of operators with different assist information on different problems.

show abstract

Section: Multiarmed Banditmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Latest Stored Information Based Adaptive Selection Strategy for Multiobjective Evolutionary Algorithm

Gao

Qing-hua

Fan

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…또 한, 최근 인터넷을 통해서 대잠수함전 임무에 위치추 정과 별도로 추적(tracking)이 추가되었음을 확인하였 고 [7,8] , 이는 소나를 이용한 현대전에서 새로이 추가된 추적 임무에 대한 중요성을 시사하고 있다. 국내에서 (multi-objective function) [17,18] 를 추적효과도 분석 알고 리즘에 적용하였다. …”

Section: Effectiveness) 분석 및 성능지표(Mop : Measure Ofunclassified

Measure of Effectiveness Analysis for Tracking in SONAR System

Cho¹,

Kim²,

Kim³

et al. 2013

Journal of the Korea Institute of Military Science and Technolo

View full text Add to dashboard Cite

Since the optimized use of sonar systems for target tracking is a practical problem for naval operations, the measure of mission achievability is needed for preparing efficient sonar-maneuver tactic. In order to quantify the mission achievability or Measure Of Effectiveness(MOE) for given sonar-maneuver tactics, we developed and tested a simulation algorithm. The proposed algorithm for tracking is based on Measure Of Performance(MOP) for localization and tracking system of sonar against target. Probability of Detection(PD) using steering beam patterns referenced to the aspect angle of sonar is presented to consider the tracking-performance of sonar. Also, the integrated software package, named as Optimal Acoustic Search Path Planning(OASPP) is used for generating sonar-maneuver patterns and vulnerability analysis for a given scenario. Through simulation of a simple case for which the intuitive solution is known, the proposed algorithm is verified.

show abstract

“…This statement is true for diverse frameworks such as Genetic [20,21] and Evolutionary Algorithms [81,98], local search [56], Differential Evolution [64,93], Memetic Frameworks [42,79] in both theoretical and application domains [55] This approximation is a set of candidate solutions that represent the theoretical Pareto set. The features that describe the quality of an approximated Pareto set have been theorised in [67].…”

Section: Introductionmentioning

confidence: 99%

Covariance matrix adaptation pareto archived evolution strategy with hypervolume-sorted adaptive grid algorithm

Rostami

Neri

2016

ICA

View full text Add to dashboard Cite

Abstract. Real-world problems often involve the optimisation of multiple conflicting objectives. These problems, referred to as multi-objective optimisation problems, are especially challenging when more than three objectives are considered simultaneously. This paper proposes an algorithm to address this class of problems. The proposed algorithm is an evolutionary algorithm based on an evolution strategy framework, and more specifically, on the Covariance Matrix Adaptation Pareto Archived Evolution Strategy (CMA-PAES). A novel selection mechanism is introduced and integrated within the framework. This selection mechanism makes use of an adaptive grid to perform a local approximation of the hypervolume indicator which is then used as a selection criterion. The proposed implementation, named Covariance Matrix Adaptation Pareto Archived Evolution Strategy with Hypervolume-sorted Adaptive Grid Algorithm (CMA-PAES-HAGA), overcomes the limitation of CMA-PAES in handling more than two objectives and displays a remarkably good performance on a scalable test suite in five, seven, and ten-objective problems. The performance of CMA-PAES-HAGA has been compared with that of a competition winning meta-heuristic, representing the state-of-the-art in this sub-field of multi-objective optimisation.The proposed algorithm has been tested in a seven-objective real-world application, i.e. the design of an aircraft lateral control system. In this optimisation problem, CMA-PAES-HAGA greatly outperformed its competitors.

show abstract

HCS: A New Local Search Strategy for Memetic Multiobjective Evolutionary Algorithms

Cited by 169 publications

References 55 publications

Latest Stored Information Based Adaptive Selection Strategy for Multiobjective Evolutionary Algorithm

Latest Stored Information Based Adaptive Selection Strategy for Multiobjective Evolutionary Algorithm

Measure of Effectiveness Analysis for Tracking in SONAR System

Covariance matrix adaptation pareto archived evolution strategy with hypervolume-sorted adaptive grid algorithm

Contact Info

Product

Resources

About